{ "best_metric": 10.908712387084961, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.11977840994160803, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0023955681988321606, "grad_norm": 8.56820011138916, "learning_rate": 5e-05, "loss": 177.7081, "step": 1 }, { "epoch": 0.0023955681988321606, "eval_loss": 11.104323387145996, "eval_runtime": 3.1886, "eval_samples_per_second": 882.198, "eval_steps_per_second": 110.392, "step": 1 }, { "epoch": 0.004791136397664321, "grad_norm": 7.576857566833496, "learning_rate": 0.0001, "loss": 177.6302, "step": 2 }, { "epoch": 0.007186704596496482, "grad_norm": 7.294190406799316, "learning_rate": 9.989294616193017e-05, "loss": 177.6665, "step": 3 }, { "epoch": 0.009582272795328643, "grad_norm": 7.69305944442749, "learning_rate": 9.957224306869053e-05, "loss": 177.4335, "step": 4 }, { "epoch": 0.011977840994160802, "grad_norm": 7.73663330078125, "learning_rate": 9.903926402016153e-05, "loss": 177.3329, "step": 5 }, { "epoch": 0.014373409192992964, "grad_norm": 7.60929012298584, "learning_rate": 9.829629131445342e-05, "loss": 177.4042, "step": 6 }, { "epoch": 0.016768977391825122, "grad_norm": 7.907179832458496, "learning_rate": 9.73465064747553e-05, "loss": 177.2313, "step": 7 }, { "epoch": 0.019164545590657285, "grad_norm": 7.655498504638672, "learning_rate": 9.619397662556435e-05, "loss": 177.0812, "step": 8 }, { "epoch": 0.021560113789489445, "grad_norm": 8.101557731628418, "learning_rate": 9.484363707663442e-05, "loss": 176.8768, "step": 9 }, { "epoch": 0.023955681988321605, "grad_norm": 8.103370666503906, "learning_rate": 9.330127018922194e-05, "loss": 176.8, "step": 10 }, { "epoch": 0.026351250187153764, "grad_norm": 8.466952323913574, "learning_rate": 9.157348061512727e-05, "loss": 176.7253, "step": 11 }, { "epoch": 0.028746818385985928, "grad_norm": 9.051348686218262, "learning_rate": 8.966766701456177e-05, "loss": 176.6347, "step": 12 }, { "epoch": 0.031142386584818087, "grad_norm": 10.276004791259766, "learning_rate": 8.759199037394887e-05, "loss": 176.3699, "step": 13 }, { "epoch": 0.033537954783650244, "grad_norm": 9.616839408874512, "learning_rate": 8.535533905932738e-05, "loss": 176.5179, "step": 14 }, { "epoch": 0.03593352298248241, "grad_norm": 8.064969062805176, "learning_rate": 8.296729075500344e-05, "loss": 176.2205, "step": 15 }, { "epoch": 0.03832909118131457, "grad_norm": 8.276692390441895, "learning_rate": 8.043807145043604e-05, "loss": 176.1893, "step": 16 }, { "epoch": 0.04072465938014673, "grad_norm": 8.38676643371582, "learning_rate": 7.777851165098012e-05, "loss": 175.9924, "step": 17 }, { "epoch": 0.04312022757897889, "grad_norm": 8.487807273864746, "learning_rate": 7.500000000000001e-05, "loss": 176.0298, "step": 18 }, { "epoch": 0.04551579577781105, "grad_norm": 8.235427856445312, "learning_rate": 7.211443451095007e-05, "loss": 175.8446, "step": 19 }, { "epoch": 0.04791136397664321, "grad_norm": 8.393233299255371, "learning_rate": 6.91341716182545e-05, "loss": 175.8286, "step": 20 }, { "epoch": 0.05030693217547537, "grad_norm": 8.528432846069336, "learning_rate": 6.607197326515808e-05, "loss": 175.5943, "step": 21 }, { "epoch": 0.05270250037430753, "grad_norm": 8.452741622924805, "learning_rate": 6.294095225512603e-05, "loss": 175.6538, "step": 22 }, { "epoch": 0.05509806857313969, "grad_norm": 8.749396324157715, "learning_rate": 5.9754516100806423e-05, "loss": 175.4764, "step": 23 }, { "epoch": 0.057493636771971855, "grad_norm": 9.00334358215332, "learning_rate": 5.6526309611002594e-05, "loss": 175.5023, "step": 24 }, { "epoch": 0.059889204970804015, "grad_norm": 11.777803421020508, "learning_rate": 5.327015646150716e-05, "loss": 174.9095, "step": 25 }, { "epoch": 0.059889204970804015, "eval_loss": 10.954909324645996, "eval_runtime": 3.1802, "eval_samples_per_second": 884.535, "eval_steps_per_second": 110.685, "step": 25 }, { "epoch": 0.062284773169636175, "grad_norm": 9.46205997467041, "learning_rate": 5e-05, "loss": 175.2977, "step": 26 }, { "epoch": 0.06468034136846833, "grad_norm": 9.183752059936523, "learning_rate": 4.6729843538492847e-05, "loss": 175.2801, "step": 27 }, { "epoch": 0.06707590956730049, "grad_norm": 8.558121681213379, "learning_rate": 4.347369038899744e-05, "loss": 175.2166, "step": 28 }, { "epoch": 0.06947147776613266, "grad_norm": 8.484734535217285, "learning_rate": 4.0245483899193595e-05, "loss": 174.8744, "step": 29 }, { "epoch": 0.07186704596496482, "grad_norm": 8.714923858642578, "learning_rate": 3.705904774487396e-05, "loss": 175.0211, "step": 30 }, { "epoch": 0.07426261416379698, "grad_norm": 8.488415718078613, "learning_rate": 3.392802673484193e-05, "loss": 174.8316, "step": 31 }, { "epoch": 0.07665818236262914, "grad_norm": 8.18109130859375, "learning_rate": 3.086582838174551e-05, "loss": 175.0143, "step": 32 }, { "epoch": 0.0790537505614613, "grad_norm": 8.661060333251953, "learning_rate": 2.7885565489049946e-05, "loss": 174.7379, "step": 33 }, { "epoch": 0.08144931876029346, "grad_norm": 8.508981704711914, "learning_rate": 2.500000000000001e-05, "loss": 174.9346, "step": 34 }, { "epoch": 0.08384488695912562, "grad_norm": 9.159597396850586, "learning_rate": 2.2221488349019903e-05, "loss": 174.6507, "step": 35 }, { "epoch": 0.08624045515795778, "grad_norm": 8.949252128601074, "learning_rate": 1.9561928549563968e-05, "loss": 174.7154, "step": 36 }, { "epoch": 0.08863602335678994, "grad_norm": 9.569437980651855, "learning_rate": 1.703270924499656e-05, "loss": 174.7043, "step": 37 }, { "epoch": 0.0910315915556221, "grad_norm": 10.044833183288574, "learning_rate": 1.4644660940672627e-05, "loss": 174.1966, "step": 38 }, { "epoch": 0.09342715975445426, "grad_norm": 9.590546607971191, "learning_rate": 1.2408009626051137e-05, "loss": 174.6522, "step": 39 }, { "epoch": 0.09582272795328642, "grad_norm": 9.014169692993164, "learning_rate": 1.0332332985438248e-05, "loss": 174.4888, "step": 40 }, { "epoch": 0.09821829615211858, "grad_norm": 8.86300277709961, "learning_rate": 8.426519384872733e-06, "loss": 174.5956, "step": 41 }, { "epoch": 0.10061386435095074, "grad_norm": 8.651285171508789, "learning_rate": 6.698729810778065e-06, "loss": 174.5091, "step": 42 }, { "epoch": 0.1030094325497829, "grad_norm": 8.819639205932617, "learning_rate": 5.156362923365588e-06, "loss": 174.5733, "step": 43 }, { "epoch": 0.10540500074861506, "grad_norm": 8.909255027770996, "learning_rate": 3.8060233744356633e-06, "loss": 174.4541, "step": 44 }, { "epoch": 0.10780056894744722, "grad_norm": 8.350724220275879, "learning_rate": 2.653493525244721e-06, "loss": 174.5568, "step": 45 }, { "epoch": 0.11019613714627938, "grad_norm": 8.798490524291992, "learning_rate": 1.70370868554659e-06, "loss": 174.4877, "step": 46 }, { "epoch": 0.11259170534511154, "grad_norm": 8.335972785949707, "learning_rate": 9.607359798384785e-07, "loss": 174.7281, "step": 47 }, { "epoch": 0.11498727354394371, "grad_norm": 8.740706443786621, "learning_rate": 4.277569313094809e-07, "loss": 174.5383, "step": 48 }, { "epoch": 0.11738284174277587, "grad_norm": 8.83700942993164, "learning_rate": 1.0705383806982606e-07, "loss": 174.5981, "step": 49 }, { "epoch": 0.11977840994160803, "grad_norm": 11.058894157409668, "learning_rate": 0.0, "loss": 174.0668, "step": 50 }, { "epoch": 0.11977840994160803, "eval_loss": 10.908712387084961, "eval_runtime": 3.1797, "eval_samples_per_second": 884.671, "eval_steps_per_second": 110.702, "step": 50 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 25, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 1, "early_stopping_threshold": 0.0 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 38111123865600.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }